JSON FilterSAFE
JSON MCP server to filter only relevant data for your LLM
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/kehvinbehvin-json-mcp-filter)
A powerful Model Context Protocol (MCP) server that provides JSON schema generation and filtering tools for local files and remote HTTP/HTTPS endpoints. Built with quicktype for robust TypeScript type generation.
Perfect for: Filtering large JSON files and API responses to extract only relevant data for LLM context, while maintaining type safety.
✨ Key Features
- 🔄 Schema Generation - Convert JSON to TypeScript interfaces using quicktype
- 🎯 Smart Filtering - Extract specific fields with shape-based filtering
- 🌐 Remote Support - Works with HTTP/HTTPS URLs and API endpoints
- 📦 Auto Chunking - Handles large datasets with automatic 400KB chunking
- 🛡️ Size Protection - Built-in 50MB limit with memory safety
- ⚡ MCP Ready - Seamless integration with Claude Desktop and Claude Code
- 🚨 Smart Errors - Clear, actionable error messages with debugging info
🛠️ Available Tools
json_schema
Generates TypeScript interfaces from JSON data.
Parameters:
filePath: Local file path or HTTP/HTTPS URL
Example:
// Input JSON
{"name": "John", "age": 30, "city": "New York"}
// Generated TypeScript
export interface GeneratedType {
name: string;
age: number;
city: string;
}json_filter
Extracts specific fields using shape-based filtering with automatic chunking for large datasets.
Parameters:
filePath: Local file path or HTTP/HTTPS URLshape: Object defining which fields to extractchunkIndex(optional): Chunk index for large datasets (0-based)
Auto-Chunking:
- ≤400K
654db8a72717OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add json-mcp-filter -- npx -y [email protected]
{
"mcpServers": {
"json-mcp-filter": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (5)
4 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
HttpJsonStrategy | read | Fetches JSON data from HTTP/HTTPS URLs (static files and API endpoints) |
LocalFileStrategy | read | Reads JSON data from local file system with 50MB size limit |
json_dry_run | write | Analyze the size breakdown of JSON data using a shape object to determine granularity. Returns size information in bytes for each specified field, mirroring the shape structure but with size values instead of data. |
json_filter | read | Filter JSON data using a shape object to extract only the fields you want. Provide filePath (local file or HTTP/HTTPS URL) and shape parameters. |
json_schema | read | Generate TypeScript schema for a JSON file or remote JSON URL. Provide the file path or HTTP/HTTPS URL as the only parameter. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, quicktype-core, zod, @types/node, typescript
Gates applied: no_behavioural_pass.
654db8a72717full audit observations/trust-audit/mcp-server/kehvinbehvin__json-filter.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 654db8a72717 | SAFE | B | 89 | first audit |
Questions
What is the JSON Filter MCP server?
JSON MCP server to filter only relevant data for your LLM
What tools does JSON Filter expose?
5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is JSON Filter safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does JSON Filter need?
No credential environment variables were found in its source, so it appears to need none.
How does JSON Filter run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as json-mcp-filter at 1.1.0.
How current is this page?
The grade is for one exact copy of the source (654db8a72717), read on 2026-10-09. The repository is watched and re-audited when it changes.